Share your thoughts, 1 month free Claude Pro on usSee more

Web Navigation on WebVoyager (test)

87Success Rate

OpenAI-CUA

Updated 1mo ago

Evaluation Results

Method	Links
OpenAI-CUA 2026.02		87
UI-TARS-1.5 2026.02		84.8
Claude-3.7 2026.02		84.1
Holo2-30B-A3B 2026.02		83
Holo2-4B 2026.02		80.2
Holo2-8B 2026.02		80.2
UI-Venus-1.5-30B-A3B 2026.02		76
UI-Venus-1.5-8B 2026.02		70.8
WebVoyager 2026.02		59.1
UI-Venus-1.5-2B 2026.02		56.4
GPT-4o 2026.02		55.5
Qwen3-VL-30B-A3B 2026.02		47.5
Qwen3-VL-8B 2026.02		45.2
Qwen3-VL-2B 2026.02		35.2